WO2016181554A1 - Computer system including server storage system - Google Patents

Abstract

A server storage system has a plurality of logic partitions obtained by logically dividing at least a portion of a plurality of resources in which a plurality of types of resources are included. The plurality of resources includes a plurality of server resources including a plurality of types of server resources possessed by the server system, and a plurality of storage resources including a plurality of types of storage resources possessed by the storage system. The resources assigned to each of two or more logic partitions include exclusively assigned resources and/or commonly assigned resources. The types of the plurality of resources that are exclusively assigned to each of the two or more logic partitions differ in the load characteristics, which are characteristics of the load on the logic partition.

Description

Computer system including server storage system

The present invention relates generally to server storage system resource allocation.

A server storage system having a server and a storage is known. There is a need to aggregate a plurality of application programs (APP) in such a server storage system. A server storage system resource is logically divided so that the performance of any APP does not affect the performance of any other APP, and different APPs are executed using different logically divided resources. It is desirable. According to Patent Document 1, the resources of the server and the storage system can be logically divided by exclusively allocating to a plurality of APPs.

Japanese Patent No. 4227035

If the logical partitioning from the server to the storage as described above, the influence of the adjacent logical partition can be suppressed. However, even when a resource larger than the allocated resource is required, the resource allocated exclusively to another logical partition cannot be used. Therefore, if logical division is performed for all logical divisions as in the prior art, resource utilization efficiency decreases.

Therefore, in the present application, it is an object to realize both improvement of the aggregation rate of coexisting application programs and prevention of performance influence.

The computer system has a server storage system. The server storage system has a plurality of logical partitions obtained by logically dividing at least a part of a plurality of resources including a plurality of types of resources. The plurality of resources includes a plurality of server resources including a plurality of types of server resources included in the server system, and a plurality of storage resources including a plurality of types of storage resources included in the storage system. The resource allocated to each of the two or more logical partitions includes at least one of a dedicated allocated resource and a shared allocated resource. A resource that is exclusively assigned to a logical partition is a resource that is occupied by that logical partition. A resource shared and allocated to a logical partition is a resource that can be shared by at least two logical partitions including the logical partition. For each of the two or more logical partitions, the types of resources that are exclusively allocated differ depending on the load characteristics of the load on the logical partition. The “computer system” referred to here may be the server storage system itself, or may include a server storage system and its management system. The “load characteristic of the load on the logical partition” may be a load characteristic of a load on a resource (for example, a CPU or an HBA port described later) allocated to the logical partition or provided to the logical partition. It may be a load characteristic of a load on the resource (for example, VOL described later). Further, the “load characteristic” may be an expected (predicted) load characteristic or a load characteristic obtained as an actual measurement value. Further, the “assigned resource” to the logical partition is a resource that becomes a component of the logical partition as a result of the assignment. On the other hand, the “provided resource” for a logical partition is a resource used by the logical partition (or an external device (or computer program) that uses the logical partition) (typically, one configuration of the logical partition). Not treated as an element).

It is possible to realize both improvement of APP aggregation rate and prevention of performance impact.

1 shows a configuration of a computer system according to a first embodiment. Some examples of server storage system resource allocation (logical partitioning) are shown. The structural example of an I / O size table is shown. The structural example of an allocation policy table is shown. The structural example of an integrated LPAR size template table is shown. The structural example of a VOL template table is shown. The structural example of an integrated LPAR table is shown. The structural example of a server LPAR table is shown. The structural example of a server LPAR / HBA table is shown. The structural example of a server HBA table is shown. The structural example of a storage HBA table is shown. The structural example of a server / storage connection table is shown. The structural example of a storage partition table is shown. A configuration example of a storage partition creation screen is shown. The structural example of an integrated LPAR creation screen is shown. An example of the flow of storage partition creation processing is shown. An example of the flow of integrated LPAR creation processing is shown. An example of each of copy and movement of integrated LPAR according to the second embodiment is shown. An example of the flow of integrated LPAR copy processing is shown. An example of the flow of integrated LPAR movement processing is shown. 2 shows an example of the configuration of a server storage system. The structural example of an integrated management server is shown. An example of the monitoring result screen which concerns on Example 3 is shown.

An example will be described below.

In the following description, information may be described using the expression “xxx table”, but the information may be expressed in any data structure. That is, “xxx table” can be referred to as “xxx information” to indicate that the information does not depend on the data structure. In the following description, the configuration of each table is an example, and one table may be divided into two or more tables, or all or part of the two or more tables may be a single table. Good.

In the following description, ID or name is used as element identification information, but other types of identification information may be used instead or in addition.

Moreover, in the following description, when explaining without distinguishing the same kind of element, a reference code (or a common code in the reference sign) is used, and when distinguishing and explaining the same kind of element, element identification information (element ID (identification information such as ID or name) (or reference numerals) may be used.

In the following description, an I / O (Input / Output) request is a write request or a read request, and may be referred to as an access request.

In the following description, the process may be described with “program” as the subject, but the program is executed by a processor (for example, a CPU (Central Processing Unit)) so that a predetermined process can be appropriately performed. Since the processing is performed using a storage unit (for example, a memory) and / or an interface device (for example, a communication port), the subject of processing may be a processor. The processing described with the program as the subject may be processing performed by a processor or an apparatus or system having the processor. The processor is an example of a control unit, and may include a hardware circuit that performs part or all of the processing. The program may be installed in a computer-like device from a program source. The program source may be, for example, a storage medium that can be read by a program distribution server or a computer. When the program source is a program distribution server, the program distribution server may include a processor (for example, a CPU) and a storage unit, and the storage unit may further store a distribution program and a program to be distributed. Then, the processor of the program distribution server executes the distribution program, so that the processor of the program distribution server may distribute the distribution target program to other computers. In the following description, two or more programs may be realized as one program, or one program may be realized as two or more programs.

In the following description, the management system may be composed of one or more computers. Specifically, for example, when the management computer displays information (specifically, for example, the management computer displays information on its own display device, or the management computer (eg, management server) displays the information for display). A remote display computer (for example, when transmitting to a management client), the management computer is a management system. For example, when a function equivalent to that of the management computer is realized by a plurality of computers, the plurality of computers (may include a display computer when the display computer performs display) is the management system. . The management computer (eg, management system) may include an interface device connected to an I / O system including a display system, a storage unit (eg, memory), and a processor connected to the interface device and the storage unit. The display system may be a display device included in the management computer or a display computer connected to the management computer. The I / O system may be an I / O device (for example, a keyboard and a pointing device or a touch panel) included in the management computer, a display computer connected to the management computer, or another computer. “Displaying display information” by the management computer means displaying the display information on the display system, which may be displaying the display information on a display device included in the management computer. The management computer may transmit display information to the display computer (in the latter case, the display information is displayed by the display computer). The management computer inputting / outputting information may be inputting / outputting information to / from an I / O device of the management computer, or a remote computer connected to the management computer (for example, a display) Information may be input / output to / from the computer. The information output may be a display of information.

In the following description, the “server LPAR” is an LPAR that occupies at least one of a plurality of resources of the server. A “storage partition” is an LPAR that occupies at least one of a plurality of storage resources.

Also, in the following description, “integrated LPAR” is a convenient term representing an LPAR to which both a server resource and a storage resource are allocated, and is an example of a logical partition. In other words, it is a unit that logically divides server and storage resources in the system. In the present embodiment, the integrated LPAR typically includes at least a part of the server LPAR and at least a part of the storage partition. Both the server resource and the storage resource allocated to the integrated LPAR may be either a dedicated allocated resource or a shared allocated resource. Specifically, for example, at least one server resource may be exclusively allocated to the integrated LPAR, and at least one storage resource may be exclusively allocated or shared. Further, for example, at least one server resource may be shared and allocated to the integrated LPAR, and at least one storage resource may be allocated or shared.

In the following description, the “resource” may be a component included in each of the servers and storages that constitute the server storage system. As components, there are physical components (for example, CPU, memory, HBA (Host Bus Adapter), port, drive (physical storage device)) and logical components (for example, VOL (logical volume)). Also, elements existing outside the server and storage, for example, a relay device existing between the server and the storage (for example, a switch having a routing function or a port expansion device not having a routing function), a relay device existing between the servers Any of the relay devices existing between the storages may be treated as an example of “resource”. Such relay device components (eg, ports, cores (controllers)) may also be treated as examples of “resources”.

In the following description, “X is exclusively allocated to Y1” means that X (for example, resource) is allocated to Y1 (for example, the first integrated LPAR) and Y2 (for example, another object of the same type as Y1) Means that it is not assigned to the second integrated LPAR). As a result, X will be occupied by Y1. On the other hand, “X is shared and assigned to Y1” means that X is assigned to Y1 but can also be assigned to Y2. As a result, X can be shared by Y1 and Y2.

Also, in the following description, “occupied resource” is a resource that is exclusively allocated, and “shared resource” is a resource that is allocated to share.

FIG. 1 shows a configuration of a computer system according to the first embodiment.

The computer system includes a server storage system 1000, an integrated management server 140 that manages the server storage system 1000, and one or more APP management servers 160 that manage a plurality of APP (application programs) 104 aggregated in the server storage system 1000. Have In the illustrated example, APP 104 includes APP-a and APP-b, and APP management server 160 includes an APP management server 160a that manages APP-a and an APP management server 160b that manages APP-b.

The server storage system 1000 includes one or more servers 100 and one or more storages 120. The server 100 is a server system (one or more server devices) having a plurality of resources (a plurality of types of resources) such as a CPU and a memory. The storage 120 is a storage system (one or more storage devices) having a plurality of resources (a plurality of types of resources) such as a CPU and a memory. The server 100 and the storage 120 may be housed in one housing.

The integrated management server 140 executes the integrated management program 660. By executing the integrated management program 660, for example, the storage partition creation function 143 and the integrated LPAR creation function 144 are exhibited. The integrated LPAR creation function 144 provides an integrated LPAR (Logical Partitioning) creation screen 141. The storage partition creation function 143 provides a storage partition creation screen 142. Both of the screens 141 and 142 are, for example, GUI (Graphical User Interface).

The integrated LPAR creation screen 141 is a screen (FIG. 15) for inputting information necessary for creating the integrated LPAR. The storage partition creation screen 142 is a screen (FIG. 14) for inputting information necessary for creating a storage partition. The storage partition creation function 143 creates a storage partition based on information input via the storage partition creation screen 142. The integrated LPAR creation function 144 creates an integrated LPAR based on information input from the integrated LPAR creation screen 141 (or information associated with a creation instruction from the APP management server 160). The integrated LPAR creation screen 141 is a screen common to a plurality of APPs aggregated in the server storage system 1000.

The APP management server 160 executes the APP management program 163. By executing the APP management program 163, for example, the APP management function 161 is exhibited. The APP management function 161 provides an integrated LPAR creation screen 162. The integrated LPAR creation screen 162 is an integrated LPAR creation screen for the management target APP of the APP management server 160 that provides the screen 162, and may be the same as the integrated LPAR creation screen 141 in other points. The APP management function 161 generates an integrated LPAR creation instruction based on information input via the integrated LPAR creation screen 162. The information input via the screen 162 may be associated with the creation instruction. The APP management function 161 transmits the creation instruction to the integrated management server 140.

The APP management server 160 may not be provided. The integrated LPAR creation instruction may be issued only from the integrated management server 140.

FIG. 21 shows a configuration example of the server storage system 1000.

The server 100, the storage 120, the APP management server 160, and the integrated management server 140 are connected to a communication network (for example, an IP (Internet Protocol) network) 2100. The APP management server 160 can communicate with the server 100 regarding the management target APP via the communication network 2100, and can send an integrated LPAR creation instruction to the integrated management server 140. The integrated management server 140 receives an instruction to create an integrated LPAR from the APP management server 160 via the communication network 2100, or receives information (for example, the configuration of the server 100, the configuration of the storage 120, the configuration of each resource) from the server storage system 1000. Operation status etc.), storage partitions can be constructed, and integrated LPARs can be constructed.

The server 100 includes a NIC (Network Interface Card) 109, a CPU 102, a memory 103, and an HBA (Host Bus Adapter) 106. The server 100 can communicate with the APP management server 160 and the integrated management server 140 via the NIC 109.

In the server 100, a server LPAR 101 is constructed. The server LPAR 101 may execute a hypervisor that generates a VM (virtual machine) and the generated VM, or may be the VM itself. The server LPAR 101 includes one or more CPUs 102 (CPU cores) and one or more memories 103, executes at least one APP 104, and recognizes at least one VOL (logical volume) 105. The APP 104 may be a program such as a database management system or a data analysis program. The APP 104 can input / output data to / from the VOL 105 by issuing an I / O request specifying the VOL 105 recognized by the server LPAR 101. In FIG. 21, the solid line between the APP 104 and the VOL 105 indicates the association between the APP 104 and the VOL 105.

The HBA 106 is an interface device for connecting the server 100 and the storage 120. The HBA 106 includes a CTL (controller) 107 and a port 108. The CTL corresponds to the core of the HBA 106 and controls transfer of requests and responses via the HBA 106. In FIG. 21, a solid line between the VOL 105, the CTL 107, and the port 108 indicates an association between the VOL 105, the CTL 107, and the port 108. That is, the VOL 105 and the port 108 are associated with the CTL 107. The CTL 107 can send and receive I / O requests and data via the port 108 associated with the CTL 107.

In this embodiment, the resources of the server 100 are a CPU core, a memory, a port of the NIC 109, an HBA 106, a CTL 107, and a port 108.

The storage 120 includes an HBA 121, a CPU 123, a memory 124, and a drive 125.

The HBA 121 has a port 122. In FIG. 21, the solid line between the ports 122 and 108 represents the association between the ports 122 and 108. The storage 120 communicates with the server 100 (server LPAR 101) via the port 122 and the port 108 associated with the port 122. For example, according to the I / O request received by the port 122 from the server 100, the CPU 123 inputs / outputs data to / from the drive 125 specified based on the I / O request. The memory 124 may include a program executed by the CPU 123, a cache area for temporarily storing data input to and output from the drive 125, management information for controlling the storage 120, and the like. The drive 125 is a physical storage device, and is typically a nonvolatile storage device (for example, an auxiliary storage device). The drive 125 may be, for example, an HDD (Hard Disk Drive) or an SSD (Solid State Drive). A plurality of drives 125 may constitute a RAID (Redundant Array of Independent (or Inexpensive) Disks) group. The RAID group stores data according to the RAID level associated with the RAID group. The RAID group may be referred to as a parity group. The parity group may be, for example, a RAID group that stores parity.

In this embodiment, the resources of the storage 120 are the HBA 121, the port 122, the CPU 123 (or CPU core), the memory 124, and the drive 125.

The storage 120 includes a first type resource that processes a request such as an I / O request, and a second type resource that is a different type of resource from the first type resource. The first type resource is at least one of a resource related to a path through which the request passes and a resource related to processing of the request, for example, the CTL 107 of the HBA 106, the CPU 123 of the storage 120, and the like. The second type resource is, for example, the server HBA port 108, the storage HBA port 122, and the like.

The relationship of the second type resource of the first type resource is as follows, for example. That is, when the I / O transfer bandwidth from the server LPAR 101 does not change and the I / O frequency such as IOPS (I / O Per Second) increases, the load of the first type resource (for example, the ratio to the maximum load) ) Becomes larger than the load of the second type resource. On the other hand, when the I / O transfer bandwidth increases without changing the I / O frequency from the server LPAR 101, the load of the second type resource becomes larger than the load of the first type resource.

Therefore, in this embodiment, in consideration of the above-described relationship between the first type resource and the second type resource, the types of resources that the integrated management program 660 allocates to each of the plurality of integrated LPARs, as will be described later. Or, the numbers are different (in other words, the configurations of a plurality of integrated LPARs obtained by logically dividing the server storage system 1000 are different).

In this embodiment, the resources of the server 100 are the CPU 102, the memory 103, the NIC 109, the HBA 106, the CTL 107, and the HBA port 108. As a resource of the server 100, at least one other kind of resource may be adopted instead of at least one of these resources. In this embodiment, at least one type of resource of the CPU 102 and the memory 103 is always exclusively allocated to the server LPAR 101 (in other words, a component of the server LPAR 101). There is no selection of whether to do.

In this embodiment, the resources of the storage 120 are the HBA 121, the CPU 123, the memory 124 (for example, cache memory in particular), and the drive 125 (for example, in particular a RAID group). As a resource of the storage 120, at least one other type of resource may be adopted instead of at least one of these resources. The other type resource may be a pool based on a RAID group, for example. From the pool, a storage area may be allocated to a virtual VOL in accordance with Thin Provisioning.

In this embodiment, the communication protocol between the server 100 and the storage 120 is the FC (Fibre Channel) protocol, but other protocols (for example, PCI-Express) may be used. When other protocols are adopted, instead of the HBA 106 of the server 100 and the HBA 121 of the storage 120, interface devices for communication according to the adopted protocol may be adopted. Interface devices typically have one or more ports. The interface device may have a communication controller (eg, a control chip) associated with the port. The communication controller can control transmission and reception of data and requests like the CTL 107.

FIG. 2 shows some examples of resource allocation (logical division) of the server storage system 1000. In FIG. 2, names or IDs are written in the blocks representing the resources of the server storage system instead of reference numerals. In FIG. 2, the letter “L” in the vicinity of the VOL 105 (for example, VOL-a) means the I / O size “large”, and the letter “S” in the vicinity of the VOL 105 (for example, VOL-d). "Means the I / O size" small ".

<1. Prevention of influence between production system and development system>

One server storage system 1000 can be used as a production system or a development system. The production system is an operating system, for example, a system that actually provides services to customers for a fee or free of charge. On the other hand, the development system is a system under development, for example, a system in the middle of creating a configuration for providing a service, or a system in which a test is performed to determine whether or not any trouble occurs when the service is actually provided. is there.

For example, in general, in the development system, it is desirable to generate more server LPARs 101 than in the production system for execution of tests and the like. On the other hand, for the production system, it is desirable to ensure both the performance of the server LPAR 101 and the enhancement of the aggregation level of the APP 104. In the development system, a large amount of I / O may be generated when executing a load test or the like. Even when a large amount of I / O is issued, it is desirable not to affect the production system that is providing the service.

Therefore, in the present embodiment, as indicated by reference numeral 201, the integrated management program 660 is installed in the server storage system 1000 in order to suppress mutual influences at the boundary between environments such as the production system and the development system where the situation is greatly different. Are logically divided from the server 100 to the storage 120. That is, the server storage system 1000 is roughly divided into a first server storage subsystem used as a production system and a second server storage subsystem used as a development system. In other words, each resource of the server storage system 1000 is exclusively allocated to either the production system or the development system. With this configuration, the performance of the production system can be prevented from being affected by the development system.

In the present embodiment, the integrated management program 660 makes a difference between the policy for resource allocation (resource division) for the production system and the policy for resource allocation for the development system. As a result, operation suitable for the characteristics of the production system and development system can be expected. For example, in the production system, the resource type and the LPAR of the resource allocation destination (or the LPAR associated with the resource allocation destination) are used so that the performance of the server LPAR 101 can be ensured and the aggregation level of the APP 104 can be improved. Whether to occupy the resource based on at least one of the use of the APP 104 to be executed, the use of the VOL 105 recognized by the server LPAR 101, and the I / O size corresponding to the APP use and the VOL use It is determined whether to use shared allocation. On the other hand, for the development system, resources allocated to the server LPAR 101 in the development system (the CPU 102 and the memory 103 constituting the server LPAR 101 and the VOL 105 recognized by the server LPAR 101 so that more server LPARs 101 can be generated than the production system. Are all shared resources. For example, in FIG. 2, in the development system, only LPAR5 is illustrated among one or more LPARs, but CTL9, CTL10, Port-e, Port5, HBA3, CPU2, Mem. 2 and Drive 2 may be shared. Even in the development system, selection of whether to allocate resources exclusively or sharedly may be performed.

In the present embodiment, at least the server CPU core, server memory, server HBA CTL, server HBA port, storage HBA port, storage HBA, storage CPU, storage memory, and storage drive are logically divided from the server 100 to the storage 120. Is assigned to either the production system or the development system. However, such allocation may not be possible depending on the type of resource. In that case, some resources may be shared. In addition, the logical division applied from the server 100 to the storage 120 is not divided into the production system and the development system, but can be divided according to other criteria such as dividing the usage range of a plurality of customers (tenants). May be applied.

<2. Resource allocation for production system>

This embodiment is characterized in that a resource to be occupied / shared is selected with reference to I / O characteristics to be processed in each logical division, for example, a data size (I / O size). In general, the I / O size “large” is larger in I / O target data size than the I / O size “small”, so that the processing load per request is larger. Depending on the difference in characteristics, the resource type to which the load is applied differs. Therefore, in this embodiment, the resource type to be occupied is determined by taking into account the characteristics of the I / O to be processed. On the other hand, the processing load per unit time tends to be larger for the I / O size “small” than for the I / O size “large”. This is because more I / O requests with an I / O size of “small” can be issued per unit time than I / O requests with an I / O size of “large”.

Also, the characteristics of each resource are different. For example, when the I / O frequency increases without changing the I / O transfer bandwidth, the load on the first type resource becomes larger than the load on the second type resource. For example, when the I / O transfer bandwidth increases without changing the frequency of I / O from the logical partition, the load of the second type resource becomes larger than the load of the first type resource. There is.

<2-1. Prevention of effects between I / O size “large”>

As described above, whether at least the production system of the production system and the development system is to be assigned or shared for various resources is selected. As indicated by reference numerals 202 and 203, at least the server HBA port 108 and the storage HBA port 122 are shared by a plurality of server LPARs 101 (or APP 104 or VOL 105) associated with the I / O size “large”, respectively. Not. In other words, a plurality of different server HBA ports 108 and a plurality of different storage HBA ports 122 are respectively assigned to the plurality of server LPARs 101 (or APP 104 or VOL 105) associated with the I / O size “large”. (For example, occupancy is allocated). Specifically, for example, Port-a and Port1 are allocated to LPAR1 (or APP-a or VOL-a) related to the I / O size “Large” and related to the I / O size “Large”. Port-b (a server HBA port different from Port-a) and Port2 (a storage HBA port different from Port1) are allocated to another LPAR2 (or APP-b or VOL-b) attached.

Especially when processing large size I / O, the port performance is low compared to the performance of other resources, so the bandwidth per port tends to become a bottleneck. On the other hand, with the above configuration, even if the bandwidth per server HBA port and the bandwidth per storage HBA port are overloaded, the I / O sizes are “large” and “large”. On the other side, the server HBA port and the storage HBA port are not affected by the overload. As a result, it is possible to prevent an adverse effect between the I / O sizes “large”.

Here, the storage HBA 121 may be shared by a plurality of VOLs 105 each having an I / O size of “large”. According to the example of FIG. 2, the storage HBA1 is shared by VOL-a, VOL-b, and VOL-c (LPAR1 to LPAR3) of I / O size “large”. For example, the allocation policy table 146 defines that the storage HBA 121 is shared by a plurality of VOLs 105 each having an I / O size of “large” (see FIG. 4).

Also, the CTL 107, which is an upper resource of the server HBA port 108, may be assigned so as not to be shared by a plurality of server LPARs 101 (or APP 104 or VOL 105) associated with the I / O size “large”. The resource of the server storage system 1000 has a dependency, for example, a hierarchical topology configuration (the route may not exist). Among the resources above the target resource, the resource one level higher than the target resource is called “parent resource”, and among the resources below the target resource, the resource one level lower than the target resource is “child resource”. Can be said. The concept of “upper / lower” or “parent / child” of a resource may differ depending on what is being managed (eg, monitored), but may be defined according to predetermined criteria. For example, when resources are in a “connection relationship”, one resource may be lower, and the other resource that is dependent on one resource (based on one resource) may be higher. In the case of “inclusion relationship” between resources, one resource may be lower and the other resource including one resource may be higher.

<2-2. Preventing effects between I / O size “large” and I / O size “small”>

As indicated by reference numeral 204, the server LPAR 101 (or APP 104 or VOL 105) associated with the “large” I / O size and the server LPAR 101 (or APP 104 or VOL 105 associated with the “small” I / O size). At least the server HBA CTL 107 and the storage HBA 121 are not shared with the VOL 105). In other words, the server LPAR 101 (or APP 104 or VOL 105) associated with the “I / O size“ large ”and the server LPAR 101 (or APP 104 or VOL 105) associated with the“ I / O size “small” are different. A server HBA CTL 107 and a plurality of different storage HBAs 121 are allocated (for example, exclusively allocated). Specifically, for example, CTLs 5 and 6 and HBA 1 are allocated to VOL-c associated with the I / O size “large”. To VOL-d associated with the I / O size “small”, CTL7 (server HBA CTL different from CTL5 and CTL) and HBA2 (storage HBA different from HBA1) are allocated.

As described above, generally, the I / O size “large” has a larger I / O target data size than the I / O size “small”, so that the processing load on the CTL per request is larger. . Therefore, by assigning different server HBA CTL 107 and different storage HBA 121 to the server LPAR 101 (or APP 104 or VOL 105) having different I / O sizes, one of the I / O sizes “large” and “small”, In particular, even if the “large” resource is heavily loaded, the server HBA CTL 107 and the different storage HBA 121 for the other can be prevented from being affected by the heavy load.

If the storage HBA has a CTL (HBA core) that can be exclusively allocated, such as the server HBL, instead of allocating in units of storage HBA, the I / O size is “large” in units of storage HBA CTL. The allocation to the server LPAR 101 (or APP 104 or VOL 105) associated with the server LPAR 101 (or APP 104 or VOL 105) associated with the I / O size “small” may be controlled.

<2-3. Prevention of effects between I / O size “small”>

As indicated by reference numeral 205, at least the server HBA CTL 107 is not shared by a plurality of server LPARs 101 (or APP 104 or VOL 105) each associated with the I / O size “small”. In other words, a plurality of different server HBA CTLs 107 are respectively allocated (for example, occupied) to a plurality of server LPARs 101 (or APP 104 or VOL 105) respectively associated with the I / O size “small”. Specifically, for example, LPAR3 (or APP-c or VOL-d) associated with I / O size “small” is assigned CTL7, and another I / O size associated with “small” CTL8 (a server HBA CTL different from CTL7) is assigned to LPAR4 (or APP-d or VOL-e / VOL-f).

When the I / O size is small, the number of I / Os processed per unit time tends to increase, so the load on the HAB CTL increases. By occupying the HBA CTL as described above, even if the server HBA CTL is overloaded for one of the I / O sizes “small” and “small”, the I / O size “small” and The server HBA CTL for the other of the “small” is not affected by the overload. As a result, it is possible to prevent an adverse effect between the I / O sizes “small”.

It should be noted that the storage HBA 121 and the storage HBA port 122 may be shared by a plurality of VOLs 105 each having an I / O size of “small”. According to the example of FIG. 2, the storage HBA 2 and Port 4 are shared by VOL-d, VOL-e, and VOL-f with I / O size “small”. For example, the allocation policy table 146 defines that the storage HBA 121 and the storage HBA port 122 are shared by a plurality of VOLs 105 each having an I / O size of “small” (see FIG. 4).

In other words, there is no need to change the server HBA port and the storage HBA port (for example, occupancy allocation) between the I / O sizes “small”. This is because when the I / O size is “small”, the CPU 123 of the storage 120 becomes a bottleneck of I / O performance before the port.

In the above, some examples of resource allocation performed in terms of I / O size have been described.

Instead of the I / O size, resource allocation is performed based on at least one of other types of I / O characteristics such as a large number of I / Os and variations in the number of I / Os, an APP usage, and a VOL usage. You may be broken. For example, a dedicated drive may be allocated to an APP having a large number of I / Os.

The above resource allocation is performed by the integrated management program 660 of the integrated management server 140 based on the management information stored in the integrated management server 140. Details of the integrated management server 140 will be described below.

FIG. 22 shows a configuration example of the integrated management server 140.

The integrated management server 140 includes an input device (for example, a keyboard and a pointing device) 610, a display device 620, a NIC 650, a storage unit (for example, a memory) 630 for storing a computer program and information, and a CPU 640 connected thereto. Have. The input device 610 and the display device 620 may be integrated like a touch panel. Instead of the input device 610 and the display device 620, the integrated management server 140 may be connected to a display computer having an input device and a display device (for example, a personal computer operated by a system administrator). The computer program stored in the storage unit 630 is, for example, the integrated management program 660, which is executed by the CPU 640. The information stored in the storage unit 630 is, for example, management information 670. The management information 670 is information that is referred to or updated for managing the server storage system 1000, and includes information that is referred to for creating an integrated LPAR (determination of configuration, etc.). Specifically, for example, the management information 670 includes an I / O size table 145 (FIG. 3), an allocation policy table 146 (FIG. 4), an integrated LPAR size template table 147 (FIG. 5), and a VOL template table 148 (FIG. 6). ), Integrated LPAR table 149 (FIG. 7), server LPAR table 150 (FIG. 8), server LPAR / HBA table 151 (FIG. 9), server HBA table 152 (FIG. 10), storage HBA table 153 (FIG. 11), server / Storage connection table 154 (FIG. 12) and storage partition table 155 (FIG. 13) are included.

Hereinafter, each table included in the management information 670 will be described.

FIG. 3 shows a configuration example of the I / O size table 145.

The I / O size table 145 shows the relationship between the APP name, APP usage, VOL usage, and I / O size. The I / O size is the size (for example, average size) of I / O target data accompanying an I / O request from the APP 104 (an I / O request specifying the VOL 105). The I / O size is an example of an I / O characteristic for at least one of the APP 104 and the VOL 105. The I / O characteristics considered for the creation of the integrated LPAR include read / write ratio (ratio of the number of read requests to the number of write requests) instead of or in addition to the I / O size, and sequential / Random ratio (ratio between the number of sequential I / Os and the number of random I / Os) and locality (concentrated I / Os where I / Os concentrate in consecutive address ranges and I / Os over distributed address ranges) At least one of which distributed I / O is greater). When considering the combination of the I / O size and any type of I / O characteristic other than the I / O size when creating the integrated LPAR, the integrated management program 660 sets the I / O size to another type. This can be considered in preference to the I / O characteristics.

The I / O size table 145 has an entry for each APP 104. The information stored in each entry includes an APP name (or other type of APP identification information for specifying the APP) 301, an APP usage 302, a VOL usage 303, and an I / O size 304. The APP name 301 indicates the name of the APP 104. The APP usage 302 indicates the usage of the APP 104. The VOL usage 303 indicates the usage of the VOL 105 associated with the APP 104. The I / O size 304 indicates an I / O size that is the size of I / O target data from the APP 104 to the VOL 105.

In this embodiment, either OLTP (Online Transaction Processing) or OLAP (Online Analytical Processing) is adopted as an APP application. Other types of applications may be employed as the APP application.

Also, in this embodiment, either data storage or log storage is adopted as a VOL application. Other types of applications may be employed as the VOL application.

In this embodiment, as the value of the I / O size 304, “large”, which means that the I / O size is relatively large (for example, equal to or greater than a predetermined threshold), and the I / O size is relatively small. Any one of “small” meaning (for example, less than a predetermined threshold) is adopted. As the value of the I / O size 304, more than two levels (for example, three levels of large, medium, and small) may be adopted. According to the I / O size table 145, the value of the I / O size 304 is determined by the set of the APP name 301, the APP usage 302, and the VOL usage 303.

FIG. 4 shows a configuration example of the allocation policy table 146.

The allocation policy table 146 indicates a resource allocation policy according to the I / O size. The allocation policy table 146 has an entry for each allocation policy. Information stored in each entry includes an I / O size 401, a server HBA CTL 402, a server HBA port 403, a storage HBA port 404, a storage HBA 405, a storage CPU 406, a storage memory 407, and a storage drive 408.

The I / O size 401 indicates the I / O size. The server HBA CTL 402 shows the allocation method of the CTL 107. A server HBA port 403 indicates an allocation method of the port 108. The storage HBA port 404 indicates the port 122 allocation method. A storage HBA 405 indicates an allocation method of the HBA 121. The storage CPU 406 shows the allocation method of the CPU 123. The storage memory 407 indicates an allocation method of the memory 124. The storage drive 408 indicates a drive 125 allocation method.

In the allocation policy table 146, “occupied” means that the resource is allocated exclusively. “Shared” means to share. “Shared between VOLs with the same I / O size” means to share and allocate to a plurality of VOLs having the same I / O size (in other words, to allocate so that the I / O size is not shared by a plurality of VOLs having different I / O sizes). Means.

When the I / O size is “large”, the port 108 of the server HBA 106 and the port 122 of the storage HBA 121 are likely to become bottlenecks. Therefore, according to the allocation policy table 146, each of the CTL 107 of the server HBA 106, the port 108 of the server HBA 106, and the port 122 of the storage HBA 121 is exclusively allocated to the VOL having the I / O size “large”.

On the other hand, when the I / O size is “small”, the port 108 of the server HBA 106 and the port 122 of the storage HBA 121 are unlikely to become bottlenecks. However, if the CTL 107 of the server HBA 106 is a shared resource, it is affected by other loads that share the port 108 of the server HBA 106. Therefore, according to the allocation policy table 146, the port 108 of the server HBA 106 and the port 122 of the storage HBA 121 are respectively shared and allocated to the VOL having an I / O size of “small”, and the CTL 107 of the server HBA 106 is exclusively allocated. .

In this embodiment, the CTL (not shown) of the storage HBA 121 cannot be controlled. Therefore, the CTL of the storage HBA 121 is shared. When the CTL of the storage HBA 121 is shared, the load of the I / O size “small” can be greatly affected by the load of the I / O size “large”. For this reason, it is desirable to logically divide the storage HBA 121. Therefore, according to the allocation policy table 146, the storage HBA 121 is sharedly allocated to a plurality of VOLs having the same I / O size.

In addition, when the occupancy allocation is possible for the CTL of the storage HBA 121, the allocation policy table 146 may not be set to logically divide the storage HBA 121. Further, when the allocating assignment is impossible for the CTL 107 of the server HBA 106, the assignment policy table 146 may be set to logically divide the server HBA 106.

FIG. 5 shows a configuration example of the integrated LPAR size template table 147.

The integrated LPAR size template table 147 indicates the amount of server resources allocated to the integrated LPAR. The integrated LPAR size template table 147 has an entry for each template of the integrated LPAR size. Information stored in each entry includes integrated LPAR size 501, LPAR CPU core number 502, LPAR memory capacity 503, LPAR NIC port number 504, I / O size 505, HBA port number 506, and server HBA CTL number 507. is there.

The integrated LPAR size 501 indicates the size of the integrated LPAR. There are three types of large, medium and small (L / M / S) as the value of the integrated LPAR size 501, but the value may be two types or four or more types. The LPAR CPU core number 502 indicates the number of CPU cores assigned to the server LPAR 101 (the number of cores of the CPU 102). The LPAR memory capacity 503 indicates the capacity of the memory 103 allocated to the server LPAR 101.
The number of LPAR NIC ports 504 indicates the number of NIC ports (NIC 109 ports) assigned to the server LPAR 101. An I / O size 505 indicates an I / O size corresponding to the APP 104 and the VOL 105 in the server LPAR 101. The HBA port number 506 indicates the number of HBA ports 108 associated with the server LPAR 101. The server HBA CTL number 507 indicates the number of CTLs 107 associated with the server LPAR 101.

FIG. 6 shows a configuration example of the VOL template table 148.

The VOL template table 148 indicates the relationship between the APP name, the APP usage, the VOL usage, and the integrated LPAR size, the VOL capacity, and the number of VOLs. The VOL template table 148 has an entry for each VOL template. Information stored in each entry includes an APP name 601, an APP usage 602, a VOL usage 603, an integrated LPAR size 604, a VOL capacity 605, and a VOL number 606. The APP name 601, the APP application 602, the VOL application 603, and the integrated LPAR size 604 are as described above. The VOL capacity 605 indicates the capacity of the VOL 105. The VOL number 606 indicates the number of VOLs 105.

FIG. 7 shows a configuration example of the integrated LPAR table 149.

The integrated LPAR table 149 indicates information related to the integrated LPAR. The integrated LPAR table 149 has an entry for each integrated LPAR. Information stored in each entry includes an integrated LPAR ID 701, an environment 702, an APP name 703, an APP usage 704, and an integrated LPAR size 706.

Integrated LPAR ID 701 indicates the ID of the integrated LPAR. The ID of the integrated LPAR may be the same value as the ID of the server LPAR included in the integrated LPAR. An environment 702 indicates an LPAR environment (which is a production environment or a development environment) that is an environment in which the integrated LPAR is relocated. The APP name 703 indicates the name of the APP executed in the integrated LPAR. The APP application 704 indicates the APP application to be executed. The integrated LPAR size 706 indicates the size of the integrated LPAR.

FIG. 8 shows a configuration example of the server LPAR table 150.

The server LPAR table 150 represents the configuration of the server LPAR 101. The server LPAR table 150 has an entry for each server LPAR 101. Information stored in each entry includes an LPAR ID 801, a server ID 802, a CPU core number 803, a memory capacity 804, a NIC port number 805, and a NIC port allocation 806.

LPAR ID 801 indicates the ID of the server LPAR 101. The server ID 802 indicates the ID of the server 100 on which the server LPAR 101 operates. The CPU core number 803 indicates the number of cores of the CPU 102 assigned to the server LPAR 101. A memory capacity 804 indicates the capacity of the memory 103 allocated to the server LPAR 101. The NIC port number 805 indicates the number of NIC 109 ports allocated to the server LPAR 101. The NIC port assignment 806 indicates whether the port of the NIC 109 is exclusively assigned to the server LPAR 101 or shared.

FIG. 9 shows a configuration example of the server LPAR / HBA table 151.

The server LPAR / HBA table 151 indicates the relationship between the server LPAR 101 and the server HBA 106. The server LPAR / HBA table 151 has an entry for each server LPAR 101. Information stored in each entry includes an LPAR ID 901, an HBA port number 902, an HBA port assignment 903, an HBA CTL number 904, and an HBA CTL assignment 905.

LPAR ID 901 indicates the ID of the server LPAR 101 of the server 100. The HBA port number 902 indicates the number of server HBA ports 108 assigned to the server LPAR 101. The HBA port allocation 903 indicates the allocation status (occupied allocation or shared allocation) of the port 108. The HBA CTL number 904 indicates the number of CTLs 107 allocated to the server LPAR 101. The HBA CTL assignment 905 indicates the assignment state (occupied assignment or shared assignment) of the CTL 107.

FIG. 10 shows a configuration example of the server HBA table 152.

The server HBA table 152 is information regarding the server HBA 106. The server HBA table 152 has an entry for each server HBA CTL 107. Information stored in each entry includes a server ID 1001, an HBA ID 1002, a port ID 1003, a port allocation 1004, a CTL ID 1005, a CTL allocation 1006, an I / O size 1007, an allocation destination 1008, and an environment 1009.

Server ID 1001 indicates the ID of the server 100. The HBA ID 1002 indicates the ID of the HBA 106. The port ID 1003 indicates the ID of the port 108. A port assignment 1004 indicates an assignment state (occupied assignment, shared assignment or unassigned) of the port 108. The CTL ID 1005 indicates the ID of the CTL 107. A CTL assignment 1006 indicates an assignment state (occupied assignment, shared assignment or unassigned) of the CTL 107. An I / O size 1007 indicates the I / O size of the VOL 105 associated with the CTL 107. The allocation destination 1008 indicates the ID of the allocation destination server LPAR 101 of the CTL 107 (if there is no allocation destination, “unallocated” may be set). An environment 1009 indicates an environment (production or development) to which the HBA 106 belongs.

FIG. 11 shows a configuration example of the storage HBA table 153.

The storage HBA table 153 is information regarding the storage HBA 121. The storage HBA table 153 has an entry for each storage HBA port 122. Information stored in each entry includes a storage ID 1101, an HBA ID 1102, a port ID 1103, a port assignment 1104, an I / O size 1105, an assignment destination 1106, and an environment 1107.

Storage ID 1101 indicates the ID of the storage 120. The HBA ID 1102 indicates the ID of the HBA 121. The port ID 1103 indicates the ID of the port 122. The port assignment 1104 indicates the assignment state (occupied assignment, shared assignment or unassigned) of the port 122. The I / O size 1105 indicates the I / O size of the VOL 105 associated with the HBA 121. The assignment destination 1106 indicates the ID of the assignment destination server LPAR 101 of the port 122 (if there is no assignment destination, it may be “unassigned”). An environment 1107 indicates an environment (production or development) to which the HBA 121 belongs.

Control is performed so that different I / O sizes are not associated with one storage HBA 121. For example, when any one port 122 (first port 122) of the HBA 121 is assigned to the server LPAR 101 (or APP 104 or VOL 105), all other HBAs 121 having the first port 122 and the first port 122 For each of the ports 122, an I / O size (“large” or “small”) corresponding to the server LPAR 101 (or APP 104 or VOL 105) to which the first port 122 is assigned is set as the I / O size 1105. It's okay. Alternatively, for example, when the first port 122 of the HBA 121 is assigned to the server LPAR 101 (or APP 104 or VOL 105), the server LPAR 101 (first port 122 assigned to the first port 122 as the I / O size 1105 is assigned to the first port 122. Alternatively, an I / O size (“large” or “small”) corresponding to the APP 104 or the VOL 105 is set, and then the integrated management program 660 is set in each of all other ports 122 of the HBA 121 having the first port 122. Accordingly, it may be avoided that the server LPAR 101 (or the APP 104 or the VOL 105) of another I / O size is associated. When all the ports 122 of the same HBA 121 are “unassigned”, any I / O size can be associated with the HBA 121.

FIG. 12 shows a configuration example of the server / storage connection table 154.

The server / storage connection table 154 indicates a connection relationship between the server HBA port 108 and the storage HBA port 122. The server / storage connection table 154 has an entry for each set of the server HBA port 108 and the storage HBA port 122. Information stored in each entry includes a server ID 1201, a server HBA ID 1202, a server port ID 1203, a storage ID 1204, a storage HBA ID 1205, and a storage port ID 1206.

Server ID 1201 indicates the ID of the server 100. The server HBA ID 1202 indicates the ID of the server HBA 106. The server port ID 1203 indicates the ID of the server HBA port 108. A storage ID 1204 indicates the ID of the storage 120. The storage HBA ID 1205 indicates the ID of the storage HBA 121. The storage port ID 1206 indicates the ID of the storage HBA port 122. The server / storage connection table 154 may be constructed by collecting connection information from the server 100 and the storage 120.

FIG. 13 shows a configuration example of the storage partition table 155.

The storage partition table 155 is information related to the configuration of the storage partition. The storage partition table 155 has an entry for each storage partition. Information stored in each entry includes a storage partition ID 1301, an environment 1302, an HBA 1303, a CPU 1304, a memory 1305, and a drive 1306.

Storage partition ID 1301 indicates the ID of the storage partition. An environment 1302 indicates an environment (production or development) to which the storage partition belongs. The HBA 1303 indicates the ID of the HBA 121 belonging to the storage partition. The CPU 1304 indicates the ID of the CPU 123 belonging to the storage partition. A memory 1305 indicates an ID of a CLPR (Cache Logical Partition) belonging to the storage partition. CLPR is a cache memory LPAR obtained by logically dividing the memory 124 (cache memory). The drive 1306 indicates the ID of the drive 125 belonging to the storage partition.

The above is the description of each table included in the management information 670.

Next, the storage partition creation screen 142 and the integrated LPAR creation screen 141 will be described.

FIG. 14 shows a configuration example of the storage partition creation screen 142.

The storage partition creation screen 142 is a screen (for example, GUI) that receives input of information for creating a storage partition and an instruction for creating a storage partition. For example, the storage partition creation screen 142 displays a storage partition ID input UI (user interface) 1401, an environment name input UI 1402, a storage partition size selection UI 1403, and a creation instruction UI 1404.

The UI 1401 is a UI for inputting the ID of the storage partition to be created, and is, for example, a text input field. The UI 1402 is a UI for inputting the name (production or development) of the environment to which the storage partition to be created belongs, and is a text input field, for example.

The UI 1403 is a UI that accepts selection of a storage partition size, and is, for example, a plurality of radio buttons respectively corresponding to a plurality of storage partition sizes. Specifically, for example, the UI 1403 includes a table representing the relationship between the storage partition size, the number of storage HBAs 121, the number of CPUs 123, the capacity of the memory 124, and the number of drives 125. The table may be information itself included in the management information 670 or information determined by the integrated management program 660 based on information and policies included in the management information 670. Radio buttons for each storage partition size are displayed in the table of the UI 1403.

When information is input to the UIs 1401 and 1402, a storage partition desired by the system administrator is selected through the UI 1403, and the creation instruction UI 1404 is operated (for example, when the “Create” button is pressed), a storage partition is created.

FIG. 15 shows a configuration example of the integrated LPAR creation screen 141.

The integrated LPAR creation screen 141 is a screen (for example, GUI) that receives input of information for creating an integrated LPAR and an instruction to create an integrated LPAR. This is an example for obtaining the characteristics of the load on the integrated LPAR (specifically, the characteristics of the I / O to the VOL provided to the integrated LPAR) as information for creating the integrated LPAR. In this embodiment, in order to determine the load characteristics of the integrated LPAR, the APP name of the APP activated by the integrated LAPR and the input of the APP usage are received. Furthermore, the VOL VOL usage input provided to the integrated LAPR (the server LPAR included in the integrated LPAR), the size of the integrated LPAR to be created, the type of environment of the integrated LPAR (production or development), etc. You may make it receive an input. Further, for example, input of I / O characteristic information itself of an application using the integrated LPAR, for example, an I / O size may be accepted.

The integrated LPAR creation screen 141 includes, for example, an integrated LPAR ID input UI 1501, an APP selection UI 1502, an APP usage selection UI 1503, an environment selection UI 1504, an integrated LPAR size selection UI 1505, a resource allocation method selection UI 1506, and a creation instruction UI 1507. Have The integrated LPAR creation screen 141 may further include a VOL usage selection UI 1508.

The UI 1501 is a UI in which the ID of the integrated LPAR to be created is input, and is a text input field, for example. A UI 1502 is a UI that accepts selection of an APP name, and is, for example, a plurality of radio buttons respectively corresponding to a plurality of APP names. A UI 1503 is a UI that accepts selection of an APP application, and is, for example, a plurality of radio buttons respectively corresponding to a plurality of APP applications. The UI 1504 is a UI that accepts an environment selection, for example, a plurality of radio buttons respectively corresponding to a plurality of environments. The UI 1505 is a UI that accepts selection of an integrated LPAR size, and is, for example, a plurality of radio buttons respectively corresponding to a plurality of integrated LPAR sizes. The UI 1508 is a UI that accepts selection of a VOL usage, and is, for example, a plurality of check boxes respectively corresponding to a plurality of VOL usages. That is, two or more VOL applications can be selected. A UI 1506 is a UI that accepts selection of a resource allocation method, and is, for example, a plurality of radio buttons respectively corresponding to a plurality of resource allocation methods. “Fixed occupancy” means that the occupancy allocation of resources is maintained regardless of the operating status (for example, start and stop) of the server LPAR. “Dynamic occupancy” means that the resource is exclusively allocated only when the operating status of the server LPAR is activated, and means that the resource does not have to be occupied when the server LPAR is stopped. “Shared” means that all resources may be shared.

When the integrated LPAR ID is input to the UI 1501 and the APP, APP application, environment, integrated LPAR size, resource allocation method, and VOL application are selected through the UIs 1502 to 1506 and 1508, and the creation instruction UI 1507 is operated (for example, “Create” button) ), An integrated LPAR is created.

The above is the description of the storage partition creation screen 142 and the integrated LPAR creation screen 141. Note that the options (for example, storage partition size, APP, environment name, APP usage, integrated LPAR size, etc.) displayed on the screen 142 or 141 may be added, changed, or deleted as appropriate. Further, in the integrated LPAR creation screen 162 displayed on the APP management server 160, the APP displayed on the APP selection UI may be limited to the APP to be managed by the APP management server 160.

Next, processing performed in the first embodiment will be described.

FIG. 16 shows an example of the flow of storage partition creation processing.

In step 201, the integrated management program 660 displays the storage partition creation screen 142, and through the screen 142, the system administrator inputs (selects) the storage partition ID, environment name, and storage partition size, and the storage. Accepts partition creation instructions. In response to the storage partition creation instruction, step 202 and subsequent steps are performed. The storage partition corresponding to the input storage partition ID is referred to as “target storage partition” in the description of FIG.

In step 202, the integrated management program 660 transmits a RAID group creation instruction to the storage 120. The RAID group creation instruction includes information (for example, the number of drives corresponding to the selected storage partition size) input via the screen 142. As a result, in response to the creation instruction, the storage 120 creates a RAID group composed of the number of drives associated with the creation instruction. The RAID level of the RAID group may be a predetermined RAID level. When different types of drives 125 are mixed (for example, when HDD and SSD are mixed), a RAID group (for example, a RAID group of HDD or a RAID group of SSD) composed of the same type of drive is created. May be. A pool based on the created RAID group may also be created.

In step 203, the integrated management program 660 transmits a CLPR creation instruction to the storage 120. The CLAR creation instruction includes information input via the screen 142 (for example, a memory capacity corresponding to the selected storage partition size). In response to the creation instruction, the storage 120 creates a CLPR having a memory capacity associated with the creation instruction. When different types of drives 125 are mixed (for example, when HDD and SSD are mixed), a CLPR may be created for each drive type.

In step 204, the integrated management program 660 updates the storage partition table 155 based on the information input via the screen 142 and the created RAID group and CLPR information. For example, the IDs of the storage HBA 121, CPU 123, CLPAR, and drive 125 determined by the storage 120 according to the number of HBAs, the number of CPUs, the memory capacity, and the number of drives corresponding to the selected storage partition size are stored in the integrated management program from the storage 120. 660, and the integrated management program 660 inputs the ID, the input storage partition ID, and the input environment name (production or development) into an entry (in the storage partition table 155) corresponding to the target storage partition. Entry).

The determination of the storage HBA 121 and the CPU 123 may be performed in S202, S203, or another step. For example, the integrated management program 660 transmits an instruction (for example, a RAID group creation instruction, a CLPR creation instruction, or another instruction) that associates the number of HBAs and the number of CPUs corresponding to the selected storage partition size to the storage 120. Good. In response to the instruction, the storage 120 may determine the storage HBA 121 and CPU 123 to be included in the target storage partition according to the number of HBAs and CPUs associated with the instruction.

Such a storage partition creation process may be performed in the integrated LPAR creation process, but in this embodiment, the storage partition creation process is performed before the integrated LPAR creation process. In other words, the integrated LPAR creation process is started after the end of the storage partition creation process. In the storage partition creation process, a high-load process involving data movement between the drives 125 may be required. When the storage partition creation is executed in the integrated LPAR creation process, the integrated LPAR creation process starts from the end to the end. May take a long time. For this reason, shortening the time required for the integrated LPAR creation processing can be expected by performing the storage partition creation processing first.

FIG. 17 shows an example of the flow of integrated LPAR creation processing.

In step 221, the integrated management program 660 receives a storage partition ID, environment name, APP name, APP usage, VOL usage, from the system administrator (or APP administrator) via the integrated LPAR creation screen 141 (or 162). An input (selection) of the integrated LPAR size and resource allocation method and an integrated LPAR creation instruction are accepted. In response to the integrated LPAR creation instruction, step 222 and subsequent steps are performed. The integrated LPAR corresponding to the input integrated LPAR ID is referred to as “target integrated LPAR” in the description of FIG.

In step 222, the integrated management program 660 refers to the storage partition table 155 and selects a storage partition corresponding to the environment selected in step 221.

In step 223, the integrated management program 660 refers to the I / O size table 145 and identifies the I / O size corresponding to the APP, APP usage, and VOL usage selected in step 221. In step 223, the integrated management program 660 refers to the VOL template table 148, specifies the VOL usage, the VOL capacity, and the number of VOLs corresponding to the APP, APP usage, and the integrated LPAR size selected in step 221. Good. Then, the integrated management program 660 creates a VOL according to the specified number of VOLs and the VOL capacity based on the storage partition selected in Step 222, and executes the APP selected in Step 221 for the created VOL. May be assigned to the target integrated LPAR. When there are a plurality of VOL usages identified from the APP name and the APP usage, the VOL capacity and the VOL number specified in each VOL usage may be created and assigned to the target integrated LPAR.

In step 224, the integrated management program 660 determines whether or not the selected resource allocation policy is an exclusive allocation (“unique occupation” or “dynamic occupation”). If the result of this determination is affirmative (step 224: Yes), step 225 is performed. If the result of this determination is negative (step 224: No), step 232 is performed. This step is executed when the input 1506 is received.

In step 225, the integrated management program 660 determines whether or not the I / O size specified in step 223 is “large”. If the result of this determination is affirmative (step 225: Yes), step 226 is performed. If the result of this determination is negative (step 225: No), step 229 is performed. When a VOL with an I / O size “large” and a VOL with an I / O size “small” coexist (for example, VOL-c and VOL-d in FIG. 2), the integrated management program 660 uses the I / O size “ Step 226 is executed for the “large” VOL, and step 229 is executed for the VOL with the I / O size “small”.

In step 226, the integrated management program 660 occupies and allocates the storage HBA port 122 to the target integrated LPAR. Specifically, for example, the following processing is performed.
(226-1) The integrated management program 660 refers to the integrated LPAR size template table 147 and identifies the HBA port number 506 corresponding to the integrated LPAR size selected in step 221 and the I / O size “large”. .
(226-2) The following processes (226-2-1) and (226-2-2) are repeated until the same number of storage HBA ports 122 as the specified number of HBA ports 506 are allocated.
(226-2-1) The integrated management program 660 refers to the storage HBA table 153, allocates the port allocation 1104 as “unallocated” and the I / O size 1105 as “large” (or “unallocated”). The destination 1106 is “unallocated”, and the environment 1107 identifies a storage HBA port that is the same as the environment selected in step 221.
(226-2-2) The integrated management program 660 exclusively allocates the specified storage HBA port to the target integrated LPAR. Specifically, for example, the integrated management program 660 updates the port allocation 1104 to “occupied” for the entry corresponding to the identified storage HBA port (entry in the storage HBA table 153), and sets the allocation destination 1106 to step The integrated LPAR ID input at 221 is updated.

In step 227, the integrated management program 660 exclusively allocates the server HBA port 108 to the target integrated LPAR. Specifically, for example, the following processing is performed.
(227-1) The integrated management program 660 refers to the server / storage connection table 154 and identifies the server HBA port 108 connected to the storage HBA port 122 assigned in step 226.
(227-2) The integrated management program 660 exclusively allocates the specified server HBA port 108 to the target integrated LPAR. Specifically, for example, the integrated management program 660 updates the port assignment 1104 to “occupied” for the entry corresponding to the specified server HBA port 108 (entry in the server HBA table 152), and the I / O size. 1007 is updated to “Large”, and the allocation destination 1008 is updated to the integrated LPAR ID input in Step 221.

In this embodiment, the correspondence relationship between the server HBA port 108 and the storage HBA port 122 is 1: 1, but the server HBA port 108 and the storage HBA port are connected by connecting the server 100 and the storage 120 via a switch. The correspondence relationship with 122 may be 1: n, m: 1, or m: n (n and m are each an integer of 2 or more). When a plurality of server HBA ports 108 are connected to one storage HBA port 122, the integrated management program 660 refers to the server HBA table 152, the port assignment 1004 is “unassigned”, and the environment 1009, A server HBA port 108 that is the same as the environment selected in step 221 is assigned to the target integrated LPAR. By this processing, the server HBA port 108 to be assigned can be changed depending on the selected environment. That is, the server HBA port 108 can be classified according to the environment. If there is no appropriate server HBA port 108, the integrated management program 660 may return to step 226 and select another storage HBA port 122.

In step 228, the integrated management program 660 exclusively allocates the server HBA CTL 107 to the target integrated LPAR. Specifically, for example, the following processing is performed.
(228-1) The integrated management program 660 refers to the server HBA table 152 and identifies the server HBA CTL 107 connected to the server HBA port 108 that has been exclusively allocated in step 227.
(228-2) The integrated management program 660 exclusively allocates the specified server HBA CTL 107 to the target integrated LPAR. Specifically, for example, the integrated management program 660 updates the CTL allocation 1006 to “occupied” for the entry corresponding to the specified server HBA CTL 107 (entry in the server HBA table 152), and sets the I / O size 1007 to Update to “Large” and update the allocation destination 1008 to the integrated LPAR ID input in Step 221.

In step 229, the integrated management program 660 shares and allocates the storage HBA port 122 to the target integrated LPAR. Specifically, for example, the following processing is performed.
(229-1) The integrated management program 660 refers to the integrated LPAR size template table 147 and identifies the integrated LPAR size selected in step 221 and the number of HBA ports 506 corresponding to the I / O size “small”. .
(229-2) The following processes (229-2-1) and (229-2-2) are repeated until the same number of storage HBA ports 122 as the specified number of HBA ports 506 are allocated.
(229-2-1) The integrated management program 660 refers to the storage HBA table 153, the port assignment 1104 is “shared” or “unassigned”, and the I / O size 1105 is “small” (or “unassigned”). )), The allocation destination 1106 is “unallocated” and the environment 1107 identifies the storage HBA port that is the same as the environment selected in step 221.
(229-2-2) The integrated management program 660 assigns the specified storage HBA port to the target integrated LPAR in a shared manner. Specifically, for example, the integrated management program 660 updates the port allocation 1104 to “shared” for the entry corresponding to the specified storage HBA port (entry in the storage HBA table 153), and sets the allocation destination 1106 to step The integrated LPAR ID input at 221 is updated.

In step 230, the integrated management program 660 assigns the server HBA port 108 to the target integrated LPAR. Specifically, for example, the following processing is performed.
(230-1) The integrated management program 660 refers to the server / storage connection table 154 and identifies the server HBA port 108 connected to the storage HBA port 122 allocated in step 226.
(230-2) The integrated management program 660 exclusively allocates the specified server HBA port 108 to the target integrated LPAR. Specifically, for example, the integrated management program 660 updates the port allocation 1104 to “shared” for the entry corresponding to the specified server HBA port 108 (entry in the server HBA table 152), and the I / O size. 1007 is updated to “small”, and the allocation destination 1008 is updated to the integrated LPAR ID input in step 221.

As described above, a plurality of server HBA ports 108 may be connected to one storage HBA port 122. In this case, the integrated management program 660 refers to the server HBA table 152, the port assignment 1004 is “shared” or “unassigned”, and the server HBA port 108 is the same as the environment selected in the environment 1009 and step 221. Are assigned to the target integrated LPAR.

In step 231, processing similar to that in step 228 is performed. However, in step 231, the I / O size 1007 corresponding to the assigned server HBA CTL 107 is updated to “small”.

In step 232, the integrated management program 660 shares and allocates the storage HBA port 122 to the target integrated LPAR. Details are the same as in step 229.

In step 233, the integrated management program 660 shares and allocates the server HBA port 108 to the target integrated LPAR. Details are the same as in step 230.

In step 234, the integrated management program 660 shares and allocates the server HBA CTL 107 to the target integrated LPAR. Specifically, for example, the following processing is performed.
(234-1) The integrated management program 660 refers to the server HBA table 152, is connected to the server HBA port 108 that is shared and assigned in step 233, and has a CTL assignment of “shared” or “unassigned”. CTL 107 is specified.
(234-2) The integrated management program 660 shares and allocates the specified server HBA CTL 107 to the target integrated LPAR. Specifically, for example, the integrated management program 660 updates the port allocation 1104 to “shared” for the entry corresponding to the specified server HBA port 108 (entry in the server HBA table 152), and the I / O size. 1007 is updated to the I / O size specified in step 223, and the allocation destination 1008 is updated to the integrated LPAR ID input in step 221.

In step 235, the integrated management program 660 completes the integrated LPAR. Specifically, for example, the following processing is performed.
(235-1) The integrated management program 660 refers to the storage partition selected in Step 222 and the storage partition table 155, and identifies the CPU, memory, and drive belonging to the storage partition. The integrated management program 660 instructs the storage 120 to create a VOL based on the VOL capacity and the number of VOLs identified in step 223 and to use the CPU, memory, and drive belonging to the storage partition.
(235-2) The storage 120 creates the specified number of VOLs of the specified capacity on the specified drive in the storage partition specified in Step 235-1. The storage 120 is set to use the instructed CPU and memory for accessing the created VOL.
(235-3) The integrated management program 660 instructs the storage 120 to allocate the storage HBA allocated in Step 226, Step 229, and Step 232.
(235-4) The storage 120 is set so that only the storage HBA designated in step 235-3 can access the VOL created in step 235-2. With this setting, access to the VOL from another storage HBA can be prevented. It is assumed that resources including at least the CPU, memory, and storage HBA port existing in the storage system in advance are stored and managed in the integrated management server, and whether or not each resource has been allocated is also managed. .
(235-5) The integrated management program 660 refers to the integrated LPAR size template table 147 and determines the number of LPAR CPU cores 502, the LPAR memory capacity 503, and the number of LPAR NIC ports 504 corresponding to the integrated LPAR size selected in Step 221. Identify.
(235-6) The integrated management program 660 has the same number of CPU cores (cores of the CPU 102) as the specified number of CPU cores, the specified LPAR memory capacity 503, the memory 103 having the same total capacity, and the specified LPAR NIC. The server 100 is instructed to create the server LPAR 101 based on the same number of NIC ports as the number of ports 504 and the server HBA port 108 and server HBA CTL 107 assigned in steps 226 to 234.
(235-7) The server 100 allocates a CPU core, memory, NIC port, server HBA port, and server HBA CTL in accordance with the instruction in step 235-2. Note that resources including at least the number of CPU cores, memory capacity, NIC port, server HBA port, and server HBA CTL existing in the server system are stored and managed in the integrated management server, and assigned to each resource. It is assumed that the existence is also managed. The resource allocated and allocated in step 235-3 is set so as not to be allocated to the other server LPAR 101, and is set so as to be inaccessible from the APP on the other server LPAR 101. Therefore, the resource is used from the other server LPAR 101. There is nothing.
(235-8) The integrated management program 660 reflects the configuration of the created server LPAR 101 (information on the allocated resources) in the integrated LPAR table 149, the server LPAR table 150, and the server LPAR / HBA table 151.

The above is an example of the flow of integrated LPAR creation processing. With this processing, according to the I / O characteristics of the activated APP, whether to occupy or share is determined in a series of flows for both the server and storage resources, and a logical partition is formed. In the integrated LPAR creation process, it is only necessary to be able to determine the resources to be allocated, and the order of the processes is not limited to the gradual follow shown in this embodiment. However, it is necessary to consider the connection relationship with the already set resources. Specifically, a storage HBA with an I / O size of “small” is allocated to the server LPAR 101 on which an APP with an I / O size of “small” operates. In addition, the server LPAR 101 that designates the environment as the production uses only the resources belonging to the production storage partition. In addition, when sufficient resources cannot be secured for the request, for example, when an integrated LPAR cannot be created because there is no unallocated resource, the unallocated resource is prepared by moving the integrated LPAR according to the second embodiment, and then the integrated LPAR is prepared. May be created. It may be suggested to the user that the shared allocation is performed instead of the exclusive allocation, and a message indicating that the integrated LPAR cannot be created due to insufficient resources may be displayed.

Also, the I / O size table 145, the allocation policy table 146, the integrated LPAR size template table 147, the server LPAR table 150, the server LPAR / HBA table 151, the server HBA table 152, the storage HBA table 153, and the storage partition table 155 are integrated. An LPAR table 149 may be created. Further, for the subsequent management, the integrated management program 660 uses the above-mentioned tables (for example, the server LPAR / HBA table 151, the server HBA table 152, and the storage HBA table 153) for each resource. The allocation type (whether shared or exclusive) may be displayed. Specifically, for example, the allocation type for each resource may be displayed on a management screen such as the screen described in the third embodiment (FIG. 23).

According to the first embodiment, the server storage system 1000 is logically divided into the production system and the development system from the server 100 to the storage 120. As a result, the load on the development system can be prevented from adversely affecting the performance of the production system.

Also, according to the first embodiment, whether at least the production system is allocated or shared to the integrated LPAR, whether the resource is exclusively allocated or shared, the load characteristics for the VOL provided to the integrated LPAR, and the type of resource to be allocated It is determined based on. Specifically, for example, a resource from the server LPAR 101 to the storage HBA 122 is divided between a VOL with I / O size “large” and a VOL with I / O size “small”, and a VOL with I / O size “large”. The resource applied from the server LPAR 101 to the storage HBA port 122 is divided, and the resource applied from the server LPAR 101 to the server HBA CTL 107 is divided between VOLs having an I / O size “small”. With this configuration, it becomes possible to occupy and allocate specific resources in a part where the load is applied based on the I / O characteristics of APP (application) operated in the integrated LPAR (logical partition), and to improve the aggregation rate of APP. It can be expected to both prevent performance impact. In Example 1, the load characteristic is uniquely determined from a combination of at least the APP application and the VOL application among the APP name, the APP application, and the VOL application, but at least one of the APP name, the APP application, and the VOL application. Alternatively, the I / O characteristic may be specified from another element (eg, from the input of the I / O characteristic itself).

For example, according to FIG. 2, logical partitioning from the server 100 to the storage 120 and logical partitioning based on at least one of I / O characteristics, APP usage, etc. (eg, logical partitioning of the production system) are continuous. A plurality of types of resources respectively corresponding to a plurality of hierarchies are logically divided (assignment control). However, in logical partitioning, a plurality of hierarchies do not necessarily have to be strictly continuous. For example, even though the first and second resources are each a resource that can be logically divided, the third resource that is hierarchically between the first and second resources is a resource that cannot be logically divided. Sometimes it is. In this case, in the logical division of the resource from the upper level to the lower level, the intermediate resource is not logically divided. However, even in such a case, it can be said that it is substantially a logical division of resources from upper to lower (for example, logical division from the server 100 to the storage 120). Whether logical partitioning is possible or not may depend on at least one of the resource type and the storage 120 function.

Example 2 will be described. At that time, differences from the first embodiment will be mainly described, and description of common points with the first embodiment will be omitted or simplified.

In the second embodiment, at least one of copying and moving of the integrated LPAR can be performed. Here, it does not matter whether the copy / transfer destination server / storage is the same as the migration source.

FIG. 18 shows an example of each copy and move of the integrated LPAR. In the following description, a VOL recognized by the server LPAR 101 is referred to as a server VOL 10 and a VOL provided by the storage 120 is referred to as a storage VOL. The server VOL corresponds to the storage VOL. The storage VOL may be a virtual VOL to which a storage area is allocated from a pool based on the drive 125.

As the plurality of servers 100, for example, there are a first server 100t and a second server 100w. The first server 100t and the second server 100w can communicate via the switch 170. As the plurality of storages 120, for example, there are a first storage 120t and a second storage 120w. The first server 100t and the first storage 120t are logically divided from the server 100 to the storage 120, and thus have a development system and a production system. The second server 100w and the second storage 120w belong to the production system. That is, the production system includes a part of the first server 100t, a part of the first storage 120t, the second server 100w, and the second storage 120w. In the production system, a part of the first server 100t and the second server 100w are connected to both a part of the first storage 120t and the second storage 120w, respectively.

The VOL 110 is a VOL managed by a multipath program (not shown) on the server LPAR 101. The multipath program has a function of collecting a plurality of VOLs 105 that can refer to one VOL 126 on the storage 120 through a plurality of paths into one VOL 110. For example, the VOL 110u is a VOL in which the VOLs 105u and 105v are combined into one.

The VOL 105u refers to the VOL 126u via the port 108u and the port 122u. The VOL 126w is a virtual VOL that refers to the VOL 126u via the port 122z and the port 122y. The VOL 105v refers to the VOL 126w via the port 108v and the port 122w. Therefore, the VOL 105u and the VOL 105v can refer to the same VOL 126u.

The switch 170 is a switch for connecting the NIC 109. The server LPAR 101 can communicate with another server LPAR 101 via the NIC 109 and the switch 170.

The “integrated LPAR copy process” is a process for copying the VOL 126u to another environment of the same storage 120 so that the VOL 126t that is a copy of the VOL 126u can be used. The “integrated LPAR migration process” is a process for migrating data in the VOL 126u to a VOL 126x in another storage 120w so that the migration destination VOL 126x can be used.

FIG. 19 shows an example of the flow of integrated LPAR copy processing.

Before executing the integrated LPAR copy process, the integrated management program 660 receives selection of the copy target integrated LPAR and selection of the copy destination environment from the system administrator.

In step 241, the integrated management program 660 refers to the allocation policy table 146. In step 242, the integrated management program 660 determines whether the allocation state of the copy target integrated LPAR has not been changed and the allocation policy is satisfied. Specifically, for example, the integrated management program 660 includes an integrated LPAR table 149, an I / O size table 145, an allocation policy table 146, a server LPAR / HBA table 151, a server HBA table 152, and a storage HBA table. 153, it is determined whether or not the allocation status of the port 108, the CTL 107, and the port 122 allocated to the copy target integrated LPAR satisfies the allocation policy represented by the table 146.

Normally, all integrated LPARs meet the allocation policy. This is because the integrated LPAR is created based on the allocation policy table 146. However, the system administrator or a person other than the system administrator (for example, a server storage system maintenance person) connects to the integrated management server 140 or another terminal (for example, the storage 120) for the purpose of error elimination or the like. The resource allocation of the integrated LPAR may be changed from an SVP (Service Processor) (not shown). In this case, resource allocation is performed without being conscious of the allocation policy. For this reason, the allocation state of the integrated LPAR may not satisfy the allocation policy. In consideration of such a situation, in this embodiment, in the process of copying (or moving) the integrated LPAR, it is determined whether or not the allocation state of the integrated LPAR satisfies the allocation policy.

If the determination result in step 242 is affirmative (S242: No), step 243 is performed. If the determination result of step 242 is negative, step 246 is performed. Note that step 241 and step 242 may be omitted, and subsequent processing (after step 243) may be performed without confirming the policy.

In step 243, the integrated management program 660 confirms that there are unallocated resources in the copy destination environment, and determines the resources to be used. The details are determined according to the policy for the storage HBA port 122, the server HBA port 108, the server HBA CTL 107, the server CPU 102, the memory 103, and the NIC 109 in the same manner as the resource allocation process flow in the integrated LPAR creation process of FIG. Is done.

In step 244, the integrated management program 660 instructs the storage 120 to make a VOL copy. In this instruction, a predetermined copy speed may be designated. This is to prevent the copy load from affecting the performance of the other server LPAR 101. In response to the instruction, data copy between VOLs is performed at a speed equal to or lower than the designated copy speed.

In step 245, the integrated management program 660 creates the server LPAR101. Specifically, for example, the integrated management program 660 uses the resource determined in step 243, uses the VOL copied in step 244, and has the same integrated LPAR size as the copy source based on the integrated LPAR size template table 147. A server LPAR 101 is created.

In step 246, the integrated management program 660 notifies the system administrator that the configuration of the integrated LPAR has been changed. Instead of notifying the system administrator, the configuration (resource allocation) of the copy target LPAR may be automatically changed so as to satisfy the allocation policy.

FIG. 20 shows an example of the flow of the integrated LPAR movement process.

Before executing the integrated LPAR migration process, the integrated management program 660 receives selection of the migration target integrated LPAR and the destination environment from the system administrator.

The processing in steps 241, S242, and S246 is the same as that in FIG.

In step 263, the integrated management program 660 confirms that there is an unallocated resource in the destination environment and determines a resource to be used. The details are determined according to the policy for the storage HBA port 122, the server HBA port 108, the server HBA CTL 107, the server CPU 102, the memory 103, and the NIC 109 in the same manner as the resource allocation process flow in the integrated LPAR creation process of FIG. Is done.

In S264, the integrated management program 660 instructs the server 100 and the storage 120 to move the VOL.

Here, a case where the production server LPAR 101u and the VOL 126u are moved to the server 100w and the storage 120w is taken as an example. Note that it is assumed that the VOL 126u is accessed by a route using the VOL 105u before the movement.

The integrated management program 660 sets the VOL 126w to reference the VOL 126u. After completing the setting, the integrated management program 660 adds a path using the VOL 105v to the VOL 110u. After adding the route, the integrated management program 660 deletes the route using the VOL 105u. After the path is deleted, the integrated management program 660 copies the contents of the VOL 126u to the VOL 126x. Note that a copy is instructed at a predetermined copy speed so that the copy load does not affect the performance of the other server LPAR 101. After completing the copy, the integrated management program 660 switches the reference destination of the VOL 105v from the VOL 126w to the VOL 126x.

In step 265, the integrated management program 660 instructs the server 100 to move the server LPAR. Specifically, for example, the integrated management program 660 uses the resource determined in step 263, uses the VOL copied in step 263, and has the same integrated LPAR size as the copy source based on the integrated LPAR size template table 147. Create a server LPAR. At this time, the integrated management program 660 copies the contents of the memory 103 in the server LPAR 101u to the server LPAR 101w, and deletes the server LPAR 101u after the copy is completed.

According to the second embodiment, resource allocation (resource allocation according to an allocation policy) for the integrated LPAR can be taken over at the copy destination or the transfer destination of the integrated LPAR. Therefore, even if the integrated LPAR is copied or moved, both the improvement of the APP aggregation rate and the prevention of the performance influence can be maintained. In the second embodiment, the integrated LPAR relocation between the different environments in the same server 100 and the same storage 120 is an integrated LPAR copy. Similarly, integrated LPAR rearrangement between different servers 100 and different storages 120 in the same environment is integrated LPAR migration, but it is not limited to migration and may be copied.

Example 3 will be described. At that time, the differences from the first and second embodiments will be mainly described, and the description of the common points with the first and second embodiments will be omitted or simplified.

The integrated management program 660 repeatedly (for example, periodically) collects the metric values of the resources of the server storage system 1000 and registers the metric values for each resource in the management information 670. The integrated management program 660 can display a monitoring result screen representing the registered metric value and at least one of the tables 145 to 155 in the management information 670 and the monitoring result merged for each resource.

FIG. 23 shows an example of the monitoring result screen.

The monitoring result screen 2301 displays the server resource monitoring result and the storage resource monitoring result.

The server resource monitoring result is information obtained by merging the server HBA table 152, the bandwidth usage rate (an example of the metric value) of the server HBA port 108 and the server HBA CTL 107.

The storage resource monitoring result is information in which the storage HBA table 153 and the bandwidth usage rate (an example of the metric value) of the storage HBA port 122 are merged.

The system administrator can appropriately perform resource management by looking at the monitoring result screen 2301. For example, when the bandwidth usage rate of the storage HBA port 122 exceeds a certain value, if the port 122 is a shared resource, the system administrator can further allocate the port 122 to another integrated LPAR. Therefore, an operation for optimizing the resource allocation can be performed. On the other hand, if the port 122 is an occupied resource, the system administrator can determine that the assignment state of the port 122 should not be changed from the exclusive assignment to the shared assignment.

Although several embodiments have been described above, these are merely examples for explaining the present invention, and the scope of the present invention is not limited to these embodiments. The present invention can be implemented in various other forms. For example, in the above-described embodiment, the load characteristic to the integrated LPAR is a load characteristic (for example, I / O characteristic) expected (predicted) based on the APP use and the VOL use. It may be a load characteristic (for example, an I / O characteristic) obtained as a value.

100: server, 120: storage system

Claims (15)

1. A server storage system including a server system and a storage system;
   The server storage system has a plurality of logical partitions obtained by logically dividing at least a part of a plurality of resources including a plurality of types of resources,
   The plurality of resources includes a plurality of server resources including a plurality of types of server resources included in the server system, and a plurality of storage resources including a plurality of types of storage resources included in the storage system,
   The resource allocated to each of the two or more logical partitions includes at least one of a dedicated allocated resource and a shared allocated resource,
   A resource that is exclusively allocated to a logical partition is a resource that is dedicated to that logical partition.
   A resource that is shared and assigned to a logical partition is a resource that can be shared by at least two logical partitions including the logical partition;
   For each of the two or more logical partitions, the types of resources that are exclusively allocated differ depending on the load characteristics of the load on the logical partitions.
   Computer system.
2. A resource is allocated to each of the two or more logical partitions according to a resource allocation policy corresponding to a load characteristic of the logical partition among a plurality of resource allocation policies.
   Each of the plurality of resource allocation policies is a policy in which it is defined whether to allocate each of two or more resource types as exclusive or shared.
   The computer system according to claim 1.
3. In each of the two or more logical partitions, an application program (APP) that issues an I / O request for a logical volume (VOL) provided by the storage system is executed.
   For each of the two or more logical partitions, the load characteristic of the logical partition is an I / O characteristic that is a characteristic of I / O to the VOL provided to the logical partition.
   The computer system according to claim 1.
4. For each of the two or more logical partitions, the I / O characteristics of the logical partition include an I / O size that is the size of I / O target data associated with an I / O request issued in the logical partition.
   The computer system according to claim 3.
5. For each of the two or more logical partitions, the I / O characteristics of the logical partition are based on the input of the usage of the APP executed in the logical partition and the input of the usage of the VOL of the I / O destination by the APP. The determined characteristics,
   The computer system according to claim 3.
6. The plurality of server resources include one or more controllers (CTL) of one or more first interface devices connected to the storage system, and one or more first ports of the one or more first interface devices,
   The plurality of storage resources include one or more second interface devices connected to the server system and one or more second ports of the one or more second interface devices;
   Whether at least one of the CTL, the first port, the second interface device, and the second port is occupied or shared for each of the two or more logical partitions, the VOL provided to the logical partition Depends on I / O size,
   The computer system according to claim 4.
7. Different CTLs, different first ports, and different second ports are allocated to logical partitions provided with two or more VOLs that are assumed to have a large I / O size, and a second interface device is shared and allocated.
   The second interface device to be shared and shared is shared with the logical partition provided with the VOL of the same I / O size.
   The computer system according to claim 6.
8. A different CTL and a different second interface device are allocated to a logical partition provided with a VOL with a large I / O size and a logical partition provided with a VOL with a small I / O size.
   The computer system according to claim 6.
9. Different CTLs are allocated to two or more logical partitions each provided with a VOL with a small I / O size, and a first port, a second port, and a second interface device are shared and allocated.
   The second interface device and the second port that are allocated and shared are each shared by the logical partition to which the VOL of the same I / O size is provided.
   The computer system according to claim 6.
10. The server storage system has a plurality of subsystems obtained by logically dividing from the server system to the storage system,
    A first subsystem of the plurality of subsystems is a production system that is a subsystem belonging to a production environment;
    A second subsystem of the plurality of subsystems is a development system that is a subsystem belonging to a development environment;
    The production system has the two or more logical partitions.
    The computer system according to claim 1.
11. At least one of logical partition rearrangement between different environments in the same server system and the same storage system and logical partition rearrangement between different server systems and different storage systems in the same environment is performed,
    In the relocation destination, according to the characteristics of the logical partition, whether to be exclusively allocated or shared is controlled for each resource type to be allocated, according to the characteristics of the logical partition.
    The computer system according to claim 10.
12. A management system for controlling allocation of resources of the server storage system to logical partitions;
    In each of the two or more logical partitions, an application program (APP) that issues an I / O request for a logical volume (VOL) provided by the storage system is executed.
    The management system includes:
    For each of the two or more logical partitions, accepts an input of an APP usage executed in the logical partition and an input of an I / O destination VOL usage by the APP,
    Based on the input APP usage and VOL usage, determine the I / O characteristics that are the characteristics of the I / O to the VOL provided in the logical partition;
    The computer system according to claim 1.
13. A logical partition management method in a management system for managing a server storage system including a server system and a storage system,
    The management system includes a control unit and a storage unit,
    The storage unit may occupy resource information of a plurality of resources each of the server system and the storage system and a logical partition in which each of the plurality of resources is created according to a load characteristic to the resource, or It has a policy that associates with shared allocation,
    The controller is
    Receive application identification information and instructions to create a logical partition provided to the application.
    Based on the load information obtained based on the resource information, the identification information, and the policy, a resource assigned to the logical partition is specified, and an exclusive assignment or a shared assignment is assigned to each of the specified resources. Determine whether to
    A logical partition management method, comprising: transmitting an instruction to create a logical partition to which the identified resource is allocated based on the determination to the server system and the storage system.
14. The controller is
    In addition to the identification information of the application, the application receives the usage of the application and the usage of the I / O destination volume by the application,
    14. The I / O size, which is the size of I / O target data accompanying an I / O request issued by the application, is obtained as the load characteristic based on the input information. Logical partition management method.
15. A management system for managing the server storage system;
    The management system is
    Collecting metric values for at least some of the plurality of resources;
    Displaying at least some of the resources whether they are allocated or shared, and the collected metric values;
    The computer system according to claim 1.

Images